Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 984 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1013827 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7279. Min Act: -0.0001

Data Index: 657901 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.7054. Min Act: -0.0001

Data Index: 1309656 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6943. Min Act: -0.0001

Data Index: 889706 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6823. Min Act: -0.0001

Data Index: 81500 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6697. Min Act: -0.0001

Data Index: 582911 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6375. Min Act: -0.0001

Data Index: 417029 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6008. Min Act: -0.0001

Data Index: 617527 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6226. Min Act: -0.0001

Data Index: 62792 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1104298 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6613. Min Act: -0.0001

Data Index: 1229627 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6390. Min Act: -0.0001

Data Index: 960935 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6571. Min Act: -0.0001

Data Index: 780136 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6158. Min Act: -0.0001

Data Index: 159339 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6853. Min Act: -0.0001

Data Index: 643046 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6191. Min Act: -0.0001

Data Index: 355951 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5686. Min Act: -0.0001

Data Index: 501218 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5977. Min Act: -0.0001

Data Index: 368576 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1241385 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.7757. Min Range: -0.7757

Max Act: 0.6142. Min Act: -0.0001

Data Index: 977631 (C4 (Web Text))

Max Activating Token Index: 255